© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 7495
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to actions, decisions, and evaluations in varied contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    الحياه
    -0.54
    MLLoader
    -0.54
     ligiloj
    -0.50
    цездатний
    -0.49
    DeleteBehavior
    -0.48
     surla
    -0.48
    WithIOException
    -0.47
    KommentareTeilen
    -0.47
     disambiguazione
    -0.46
    WindowConstants
    -0.45
    POSITIVE LOGITS
     taken
    1.30
     undertaken
    1.26
     received
    1.23
     delivered
    1.21
     performed
    1.18
     executed
    1.17
     achieved
    1.16
     played
    1.15
     obtained
    1.14
     submitted
    1.13
    Activations Density 1.980%

    No Known Activations